Up to date
tiiuae Apache 2.0 out 4 years ago
7.22B parameters, text in, text out.
Verified 2026-10-25 Rank #211 in LLMs · score 88.4 method v1 Sources 3 Downloads 30d 32.2k · #417 of 619 tracked
Picked by rule from 10 tracked pieces: the lab's own post, the most shared, a field report, the latest.
On 13 May, 2024, the Technology Innovation Institute released Falcon 2, an open-source model series where Falcon 2 11B scores 64.28 on the Hugging Face leaderboard, narrowly trailing Google's Gemma 7B at 64.29.
The 3 picks above, plus these 7. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 16 quantized builds and 100 Spaces.
Top Spaces running it: h2oai/h2ogpt-chatbot ♥ 295 · h2oai/h2ogpt-chatbot2 ♥ 167 · tomg-group-umd/Binoculars ♥ 76 · aimevzulari/Prompt_Uzmani ♥ 46
Weights only, an estimate: leave room for the KV cache. Method
About 4.3 GB at INT4, 8.7 GB at FP8, 17 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2023-04-25), amber triangles are 5 dated articles (each links to it), grey ticks are repo commits.
127 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Falcon-7B-Instruct is a 7.22B parameter causal decoder-only model designed for text generation.[1][2] The model is released under the Apache 2.0 license and was finetuned on a 250M token mixture of instruct and chat datasets.[3][4]
Generated 2026-10-07 15:04 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | FalconForCausalLM |
| Model type | falcon |
| Dtype | bfloat16 |
| Params by dtype | BF16: 7,217,189,760 |
| Size band | M |
| MoE | no |
| Languages | en |
| Papers | arXiv:2205.14135, arXiv:1911.02150, arXiv:2005.14165, arXiv:2104.09864, arXiv:2306.01116 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · FalconForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · FalconForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for falcon-7b-instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 17 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 8.7 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.3 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 16adapter: 81finetune: 30
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| QuantFactory/falcon-7b-instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | QuantFactory | 2 | 15.7k |
| mradermacher/falcon-7b-instruct-i1-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 0 | 5.7k |
| mradermacher/falcon-7b-instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 3k |
| tensorblock/falcon-7b-instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | tensorblock | 0 | 2.6k |
| daios/daios-demo-courage | adapter | — | — | — | — | daios | 0 | 662 |
| EmbeddingStudio/query-parser-falcon-7b-instruct | adapter | — | — | — | apache-2.0 | EmbeddingStudio | 2 | 478 |
| twhoool02/Falcon-7B-instruct-NF4 | quantized | -NF4 | 7.13B | M | other | twhoool02 | 0 | 544 |
| Amod/falcon7b-fine-tuned-therapy | adapter | — | — | — | — | Amod | 2 | 366 |
| amztheory/falcon-7b-code-python | adapter | — | — | — | apache-2.0 | amztheory | 0 | 466 |
| pcuenq/falcon-7b-instruct-gguf | quantized | gguf | — | — | apache-2.0 | pcuenq | 1 | 390 |
| OpenVINO/falcon-7b-instruct-int4-ov | quantized | int4 | — | — | apache-2.0 | OpenVINO | 0 | 440 |
| OpenVINO/falcon-7b-instruct-fp16-ov | finetune | -fp16 | — | — | apache-2.0 | OpenVINO | 0 | 425 |
| IvanD2002/Stuco_Task_Generator | quantized | — | — | — | apache-2.0 | IvanD2002 | 0 | 418 |
| Kondara/falcon-7b-instruct-Q4_K_M-GGUF | quantized | GGUF | — | — | apache-2.0 | Kondara | 0 | 376 |
| OpenVINO/falcon-7b-instruct-int8-ov | quantized | int8 | — | — | apache-2.0 | OpenVINO | 0 | 370 |
| isaacOnline/falcon-7b-instruct_finetuned | adapter | — | — | — | — | isaacOnline | 0 | 356 |
| subset-data/falcon-testing | quantized | — | — | — | — | subset-data | 0 | 327 |
| sabayo/Marcaps-GPT | adapter | — | — | — | apache-2.0 | sabayo | 0 | 320 |
| xzrderek/spongebob-llm | finetune | — | — | — | apache-2.0 | xzrderek | 0 | 307 |
| amztheory/falcon-7b-alpaca | adapter | — | — | — | apache-2.0 | amztheory | 0 | 302 |
| martintomov/falcon-7b-instruct-Q8_0-GGUF | quantized | Q8_0 | — | — | apache-2.0 | martintomov | 0 | 269 |
| macaferrari/basketball_definitive-falcon-7b | finetune | — | — | — | — | macaferrari | 0 | 264 |
| Tomasal/falcon-7b-instruct-enron | adapter | — | 6.92B | M | apache-2.0 | Tomasal | 0 | 243 |
| dH29010/falcon-7b-instruct-Q4_K_M-GGUF | quantized | GGUF | — | — | apache-2.0 | dH29010 | 0 | 234 |
| danielflopez1/falcon7binstruct_badata | adapter | — | — | — | apache-2.0 | danielflopez1 | 0 | 204 |
| pareek-yash/falcon-7b-qlora-airport-chatbot | adapter | — | — | — | — | pareek-yash | 0 | 199 |
| Aditi25/Instruct_on_sharded | adapter | — | — | — | apache-2.0 | Aditi25 | 0 | 197 |
| udemex10/Vojo_AI_LLMforCAD_v1.0 | adapter | — | 6.93B | M | — | udemex10 | 0 | 191 |
| shithumb/venus-x1 | finetune | — | — | — | apache-2.0 | shithumb | 1 | 129 |
| jianna4/finetuned_disease | finetune | — | — | — | apache-2.0 | jianna4 | 0 | 175 |
| iampanky0/New_Falcon | quantized | — | 7.03B | M | apache-2.0 | iampanky0 | 1 | 121 |
| MohammadOthman/falcon-7b-instruct-truthfulqa | adapter | — | — | — | apache-2.0 | MohammadOthman | 0 | 167 |
| themanas021/falcon-7b-instruct-Finance_Advisor | adapter | — | — | — | apache-2.0 | themanas021 | 1 | 112 |
| cphan-intersystems/falcon-7b-instruct-Q8_0-GGUF | quantized | Q8_0 | — | — | apache-2.0 | cphan-intersystems | 0 | 162 |
| cphan-intersystems/falcon-7b-instruct-Q4_K_M-GGUF | quantized | GGUF | — | — | apache-2.0 | cphan-intersystems | 0 | 160 |
| gmazur591/falcon-7b-instruct-ft-adapters | adapter | — | 6.92B | M | — | gmazur591 | 0 | 149 |
| bmanobel/falcon7b-kolt_translator_10k_800steps_5epoch | adapter | — | — | — | — | bmanobel | 0 | 143 |
| shrimali/trained_model | adapter | — | — | — | — | shrimali | 0 | 142 |
| CioMehmetAli/falcon-movie-lora-7b-instruct | adapter | — | — | — | apache-2.0 | CioMehmetAli | 0 | 140 |
| Aditi25/Instruct_copy_results_latest | adapter | — | — | — | apache-2.0 | Aditi25 | 0 | 126 |
| Date | Commit | SHA |
|---|---|---|
| 2024-10-12 | Adding `safetensors` variant of this model (#126) | 8782b5c |
| 2024-09-28 | enh: add link to new model | b22819d |
| 2024-09-16 | add chat template to tokenizer_config.json (#111) | 0b9684d |
| 2023-09-29 | Move to in-libary checkpoint (for real this time) (#88) | cf4b3c4 |
| 2023-07-13 | Revert in-library PR (#63) | eb410fb |
| 2023-07-12 | Move to in-library checkpoint (#56) | f8dac3f |
| 2023-06-26 | Add widget examples | c7f670a |
| 2023-06-09 | Add recommendations for use | 9f16e66 |
| 2023-06-05 | Update citation info | 8281cc0 |
| 2023-06-05 | Add hf endpoint handler.py (#24) | 7f5eb0f |
| 2023-06-05 | Update metadata | a1d11a0 |
| 2023-06-01 | Remove TII Falcon LLM license | 22225c3 |
| 2023-05-31 | Update license information to Apache 2.0 | 43b757f |
| 2023-05-31 | Update README.md (#14) | a8b5565 |
| 2023-05-30 | license: tii-falcon-llm (#11) | 6677bc9 |
| 2023-05-30 | Update config.json | 9cbb161 |
| 2023-05-30 | Update modelling_RW.py | 93b55b6 |
| 2023-05-30 | coreml-weights (#8) | 983c105 |
| 2023-05-26 | Add PyTorch 2.0 notice | b6efaea |
| 2023-05-26 | Add evaluation disclaimer | 6940d5f |
| 2023-05-26 | Update README.md | 5aad858 |
| 2023-05-25 | Update configuration_RW.py | 69601d5 |
| 2023-05-25 | Update modelling_RW.py | 8d630c5 |
| 2023-05-25 | Update README.md | 54b3714 |
| 2023-05-25 | Create LICENSE.txt | 7ea4d00 |
| 2023-05-25 | Update modelling_RW.py | c147e5d |
| 2023-05-24 | Upload tokenizer | bacaa8a |
| 2023-05-24 | Update configuration_RW.py | 19299bf |
| 2023-04-26 | Update README.md | e0e1228 |
| 2023-04-26 | Create README.md | e251c35 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
| Title | Source | Published | First seen | Signals |
|---|---|---|---|---|
| falcon.md | github.com | — | 2026-10-07 | exa |
| Falcon 7B Instruct By tiiuae: Benchmarks, Features and Detailed Analysis. Insights on Falcon 7B Instruct. | llm-explorer.com | — | 2026-10-07 | exa |
| Run Falcon-7B Instruct API (Easy Deployment & Flat-Rate Pricing) | featherless.ai | — | 2026-10-07 | exa |
| Falcon 2 | tii.ae official | 2024-05-13 | 2026-10-07 | hn |
| Falcon 180B | huggingface.co | 2023-09-06 | 2026-10-07 | hn |
| Falcon-7B-Instruct Model | InstructEval Models Leaderboard | accubits.com | 2023-07-17 | 2026-10-07 | exa |
| Fine tuning Falcon 7B instruct model on single commodity GPU | medium.com | 2023-06-26 | 2026-10-07 | exa |
| Falcon 40B LLM (which beats Llama) now Apache 2.0 | twitter.com | 2023-05-31 | 2026-10-07 | hn |
| A 1/48 scale model of the SpaceX Falcon Heavy rocket | bps.space | 2020-05-31 | 2026-10-07 | hn |
| Falcon is a free, open-source SQL editor with inline data visualization | github.com | 2020-04-15 | 2026-10-07 | hn |
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:36 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:04 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
